Renfield

data-ai MCP Server

Self-hosted AI assistant with voice satellites, 100+ tool integrations, RAG knowledge base, and full offline capability. Built with FastAPI + React + Ollama.

Verified
data-aidata-ai
3 views38 stars8 forksMIT

Why This Matters

Discovered via github-topic:mcp and last synced 2mo ago.

Verified
Source
github-topic:mcp
Stars
38
Last synced
2mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
17
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (17)

Search

SearXNG metasearch

Standard

No

Weather

OpenWeatherMap forecasts

n8n

Workflow automation

News

NewsAPI headlines

Jellyfin

Media server queries

DLNA

Media renderer control with gapless queue

Server

Model

Source

Trigger

Calendar

Exchange, Google, CalDAV (multi-account)

Production

No

stdio

### Knowledge Base (RAG) - **Hybrid search** — dense embeddings (pgvector) + BM25 full-text (German FTS, OR matching), combined via RRF - **Formats** — PDF, DOCX, PPTX, XLSX, HTML, Markdown, TXT (with EasyOCR fallback for garbled PDFs) - **Knowledge bases** — thematic collections with sharing and access control - **Agent tool** — `knowledge_search` for combined RAG + Paperless search within the agent loop - **Knowledge Graph** — entity-relation triples with post-extraction validation, string-similarity dedup, bulk cleanup API, admin dashboard ### Multi-Room Voice Satellites

Document

Content

Instant

- **Privacy-aware TTS** — notifications respect room occupancy (public / personal / confidential) - **Automation hooks** — `enter_room`, `leave_room`, `first_arrived`, `last_left` events fire webhooks for n8n / Home Assistant - **Presence dashboard** — real-time room occupancy in the admin UI ### Security & Access Control - Role-permission based access control (RPBAC) with JWT - Rate limiting, circuit breakers, trusted proxy support - Docker secrets management for production ### Platform - Progressive Web App (desktop, tablet, mobile) - Dark mode (light, dark, system) - Multilingual (German, English) - Prometheus metrics (opt-in) ## Quick Start ```bash git clone https://github.com/ebongard/renfield.git && cd renfield cp .env.example .env # configure your settings docker compose up -d # start the stack docker exec -it renfield-ollama ollama pull qwen3:8b # download LLM ``` Open **http://localhost:3000** and start chatting. > For GPU acceleration, use `docker compose -f docker-compose.prod.yml up -d` with NVIDIA Container Toolkit. ## Architecture <p align="center"><img src="docs/assets/architecture.png" width="900" alt="Renfield Architecture"></p> ## Configuration All settings via `.env`, loaded by Pydantic Settings. See [docs/ENVIRONMENT_VARIABLES.md](docs/ENVIRONMENT_VARIABLES.md) for the full reference. ### LLM (Multi-Model) Separate models for different tasks: ```env OLLAMA_URL=http://ollama:11434 OLLAMA_CHAT_MODEL=qwen3:14b # chat responses OLLAMA_INTENT_MODEL=qwen3:8b # intent recognition OLLAMA_RAG_MODEL=qwen3:14b # RAG answers OLLAMA_EMBED_MODEL=nomic-embed-text # embeddings (768 dim) ``` **Pluggable inference — not everything runs on Ollama.** The LLM tier speaks an OpenAI-compatible protocol, so each task can route to a different backend (`LLM_OPENAI_FOR_*`). Ollama is the simple default; the reference deployment splits inference across dedicated GPU servers:

Embeddings

**llama.cpp**

Vision

**Ollama**

File

Use Case